feat: Mastodon Post Composition and Publishing

.env.example

@@ -5,7 +5,7 @@ MASTODON_ACCESS_TOKEN=replace-me
 VISIBILITY=public
 SITE_URL=https://blog.example.com
 HASHTAGS=#throwback,#10backward
-THROWNBACK_PREFIX=Throwback:
+THROWNBACK_PREFIX=Heute vor 10 Jahren:
 MAX_RETRIES=3
 RUN_AT=09:00
 TZ=Europe/Berlin

src/tenbackward/config.py

@@ -26,7 +26,7 @@ OPTIONAL_KEYS: tuple[str, ...] = ("BLOG_REPO_URL", "BLOG_DIR")
 
 DEFAULTS = {
     "VISIBILITY": "public",
-    "THROWNBACK_PREFIX": "Throwback:",
+    "THROWNBACK_PREFIX": "Heute vor 10 Jahren:",
     "MAX_RETRIES": "3",
     "TZ": "Europe/Berlin",
     "RUN_AT": "09:00",

src/tenbackward/main.py

@@ -13,17 +13,17 @@ from .logging_setup import (
     log_run_summary,
     log_startup,
 )
-from .matching import iter_anniversary_paths
+from .matching import MatchedPost, find_anniversary_matches
+from .publishing import publish_mastodon
 from .state import PostedStore
 
 
-def _iter_candidates(config: Config) -> Iterable[str]:
-    """Yield candidate post identifiers (the relative path under
-    ``_posts/blog/``) for posts whose anniversary is exactly 10 years
-    before today.
+def _iter_candidates(config: Config) -> Iterable[MatchedPost]:
+    """Yield candidate :class:`MatchedPost` objects whose anniversary is
+    exactly 10 years before today.
     """
     post_root = config.blog_dir / "_posts" / "blog"
-    return iter_anniversary_paths(post_root, config.site_url)
+    return find_anniversary_matches(post_root, config.site_url)
 
 
 def _run_once(config: Config) -> tuple[int, int, int, int, list[str]]:
@@ -40,24 +40,24 @@ def _run_once(config: Config) -> tuple[int, int, int, int, list[str]]:
 
     store = PostedStore(config.data_dir)
 
-    scanned = 0
-    matched = 0
-    posted = 0
-    skipped = 0
-    posted_ids: list[str] = []
+    candidates = list(_iter_candidates(config))
+    scanned = len(candidates)
+    matched = len(candidates)
 
-    for candidate_id in _iter_candidates(config):
-        scanned += 1
-        matched += 1
-        if store.is_posted(candidate_id):
-            skipped += 1
+    unposted: list[MatchedPost] = []
+    for match in candidates:
+        if store.is_posted(match.path):
             continue
-        posted_ids.append(candidate_id)
-        posted += 1
+        unposted.append(match)
 
-    if posted_ids:
+    skipped = matched - len(unposted)
+    posted_ids = [m.path for m in unposted]
+
+    if unposted:
+        publish_mastodon(config, unposted)
         store.mark_posted_many(posted_ids)
 
+    posted = len(unposted)
     return scanned, matched, posted, skipped, posted_ids
 
 

src/tenbackward/matching.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import calendar
 import logging
 import re
+import unicodedata
 from dataclasses import dataclass
 from datetime import date, datetime
 from pathlib import Path
@@ -15,6 +16,8 @@ _LOGGER = logging.getLogger("tenbackward.matching")
 
 _FILENAME_PATTERN = re.compile(r"^(\d{4})-(\d{2})-(\d{2})-(.+)$")
 
+_NON_ALNUM_RE = re.compile(r"[^a-z0-9]+")
+
 _DEFAULT_TZ = "Europe/Berlin"
 
 
@@ -26,6 +29,19 @@ class MatchedPost:
     url: str
 
 
+def slugify_title(title: str) -> str:
+    """Return a URL-safe slug derived from ``title``.
+
+    Used by the matcher to derive the slug component of
+    :attr:`MatchedPost.url` from the resolved post title.
+    """
+    normalized = unicodedata.normalize("NFKD", title)
+    ascii_only = normalized.encode("ascii", "ignore").decode("ascii")
+    lowered = ascii_only.lower()
+    dashed = _NON_ALNUM_RE.sub("-", lowered)
+    return dashed.strip("-")
+
+
 def _today_in_berlin(tz_name: str = _DEFAULT_TZ) -> date:
     return datetime.now(ZoneInfo(tz_name)).date()
 
@@ -152,7 +168,7 @@ def _process_file(
         path=rel,
         title=title,
         date=post_date,
-        url=_build_url(site_url, post_date, fn_slug),
+        url=_build_url(site_url, post_date, slugify_title(title)),
     )
 
 
@@ -206,4 +222,5 @@ __all__ = [
     "MatchedPost",
     "find_anniversary_matches",
     "iter_anniversary_paths",
+    "slugify_title",
 ]  

src/tenbackward/publishing.py

@@ -0,0 +1,141 @@
+"""Mastodon publishing helpers and the API success boundary.
+
+The :func:`publish_mastodon` function is the single boundary between the
+pipeline orchestrator and the Mastodon HTTP API. Status composition and
+length validation are pure and isolated from network access so they can
+be tested without a server.
+"""
+
+from __future__ import annotations
+
+from typing import Callable
+
+from mastodon import Mastodon
+
+from .config import Config
+from .matching import MatchedPost, slugify_title
+
+
+MASTODON_STATUS_LIMIT = 500
+
+
+class PublishError(RuntimeError):
+    """Raised when status composition, validation, or the Mastodon API
+    call fails. The pipeline orchestrator treats this like any other
+    pipeline error and lets the retry budget decide whether to give up.
+    """
+
+
+def _normalize_hashtags(hashtags: str) -> str:
+    parts = [token.strip() for token in (hashtags or "").split(",")]
+    parts = [token for token in parts if token]
+    return " ".join(parts)
+
+
+def build_status_text(
+    prefix: str,
+    posts: list[MatchedPost],
+    hashtags: str,
+) -> str:
+    """Compose a single Mastodon status string for ``posts``.
+
+    The format is::
+
+        {prefix}
+
+        {title1}
+        {url1}
+
+        {title2}
+        {url2}
+
+        ...
+
+        {hashtags}
+
+    Posts are sorted by ``(date, path)`` for deterministic output
+    regardless of the upstream ordering.
+    """
+    if not posts:
+        raise PublishError("empty_posts: cannot compose status without posts")
+
+    ordered = sorted(posts, key=lambda m: (m.date, m.path))
+    blocks: list[str] = []
+    for match in ordered:
+        blocks.append(f"{match.title}\n{match.url}")
+    body = "\n\n".join(blocks)
+
+    lines: list[str] = [prefix.strip(), body]
+    tag_line = _normalize_hashtags(hashtags)
+    if tag_line:
+        lines.append(tag_line)
+    return "\n\n".join(lines) + "\n"
+
+
+def validate_status(status: str, limit: int = MASTODON_STATUS_LIMIT) -> None:
+    """Raise :class:`PublishError` when ``status`` exceeds ``limit``.
+
+    Never truncates: the spec requires failing safely rather than
+    shortening content.
+    """
+    if len(status) > limit:
+        raise PublishError(
+            f"status_too_long: len={len(status)} limit={limit}"
+        )
+
+
+def _post_status_via_mastodon_py(
+    status: str,
+    *,
+    base_url: str,
+    access_token: str,
+    visibility: str,
+    client_factory: Callable[..., Mastodon] | None = None,
+) -> None:
+    factory = client_factory if client_factory is not None else Mastodon
+    client = factory(access_token=access_token, api_base_url=base_url)
+    client.status_post(status, visibility=visibility)
+
+
+def publish_mastodon(
+    config: Config,
+    posts: list[MatchedPost],
+    *,
+    client_factory: Callable[..., Mastodon] | None = None,
+) -> str:
+    """Compose, validate, and publish ``posts`` to Mastodon.
+
+    Returns the composed status text on success. Raises
+    :class:`PublishError` on any failure (composition, length, or API).
+    The original exception is chained via ``raise ... from exc`` so the
+    caller can inspect the underlying cause.
+    """
+    try:
+        status = build_status_text(
+            config.throwback_prefix, posts, config.hashtags
+        )
+        validate_status(status)
+        _post_status_via_mastodon_py(
+            status,
+            base_url=config.mastodon_base_url,
+            access_token=config.mastodon_access_token,
+            visibility=config.visibility,
+            client_factory=client_factory,
+        )
+    except PublishError:
+        raise
+    except Exception as exc:  # noqa: BLE001 — third-party boundary
+        raise PublishError(
+            f"publish_failed: {type(exc).__name__}: {exc}"
+        ) from exc
+    return status
+
+
+__all__ = [
+    "MASTODON_STATUS_LIMIT",
+    "PublishError",
+    "build_status_text",
+    "publish_mastodon",
+    "slugify_title",
+    "validate_status",
+]

tests/test_config.py

@@ -142,7 +142,7 @@ def test_load_config_applies_optional_defaults(env_setup, monkeypatch) -> None:
     monkeypatch.delenv("TZ", raising=False)
 
     config = load_config()
-    assert config.throwback_prefix == "Throwback:"
+    assert config.throwback_prefix == "Heute vor 10 Jahren:"
     assert config.max_retries == 3
     assert config.tz == "Europe/Berlin"
     assert config.visibility == "public"

tests/test_matching.py

@@ -11,6 +11,7 @@ from tenbackward.matching import (
     MatchedPost,
     find_anniversary_matches,
     iter_anniversary_paths,
+    slugify_title,
 )
 
 
@@ -64,6 +65,7 @@ def test_match_uses_frontmatter_date_and_title(tmp_path: Path) -> None:
     assert match.title == "Foo"
     assert match.date == date(2014, 8, 4)
     assert match.url == "https://chaospott.de/2014/08/04/foo/"
+    assert match.url.endswith(slugify_title(match.title) + "/")
 
 
 def test_match_falls_back_to_filename_when_frontmatter_missing(tmp_path: Path) -> None:
@@ -87,6 +89,7 @@ def test_match_falls_back_to_filename_when_frontmatter_missing(tmp_path: Path) -
     assert match.title == "no-frontmatter"
     assert match.date == date(2015, 3, 10)
     assert match.url == "https://chaospott.de/2015/03/10/no-frontmatter/"
+    assert match.url.endswith(slugify_title(match.title) + "/")
 
 
 def test_unpublished_post_is_skipped(tmp_path: Path) -> None:

tests/test_publishing.py

@@ -0,0 +1,191 @@
+from __future__ import annotations
+
+import os
+from datetime import date
+from pathlib import Path
+from typing import Callable
+
+import pytest
+
+from tenbackward.config import load_config
+from tenbackward.matching import MatchedPost
+from tenbackward.publishing import (
+    MASTODON_STATUS_LIMIT,
+    PublishError,
+    build_status_text,
+    publish_mastodon,
+    slugify_title,
+    validate_status,
+)
+from tenbackward.state import PostedStore
+
+
+def _make_match(path: str, title: str, day: int = 4) -> MatchedPost:
+    return MatchedPost(
+        path=path,
+        title=title,
+        date=date(2016, 8, day),
+        url=f"https://blog.example.com/2016/08/{day:02d}/{path.split('-', 3)[-1].removesuffix('.md')}/",
+    )
+
+
+class _FakeMastodon:
+    """Captures ``status_post`` calls and can be configured to raise."""
+
+    def __init__(self, *, raise_on_post: Exception | None = None) -> None:
+        self.raise_on_post = raise_on_post
+        self.calls: list[tuple[str, dict]] = []
+
+    def __call__(self, *, access_token: str, api_base_url: str) -> "_FakeMastodon":
+        self.access_token = access_token
+        self.api_base_url = api_base_url
+        return self
+
+    def status_post(self, status: str, **kwargs) -> None:
+        self.calls.append((status, kwargs))
+        if self.raise_on_post is not None:
+            raise self.raise_on_post
+
+
+@pytest.fixture()
+def full_config(env_setup, tmp_path: Path):
+    os.environ["DATA_DIR"] = str(tmp_path)
+    return load_config()
+
+
+def test_slugify_title_basic_ascii() -> None:
+    assert slugify_title("Hello, World!") == "hello-world"
+
+
+def test_slugify_title_collapses_repeats_and_trims() -> None:
+    assert slugify_title("!!!Foo---Bar???") == "foo-bar"
+    assert slugify_title("---trim---me---") == "trim-me"
+
+
+def test_build_status_text_single_post_layout() -> None:
+    match = _make_match("2016/2016-08-04-foo.md", "Foo")
+    status = build_status_text(
+        "Heute vor 10 Jahren:", [match], "#throwback,#10backward"
+    )
+    assert status == (
+        "Heute vor 10 Jahren:\n\n"
+        "Foo\nhttps://blog.example.com/2016/08/04/foo/\n\n"
+        "#throwback #10backward\n"
+    )
+
+
+def test_build_status_text_multiple_posts_combined() -> None:
+    match_a = _make_match("2016/2016-08-04-a.md", "Alpha")
+    match_b = _make_match("2016/2016-08-04-b.md", "Bravo")
+    status = build_status_text("P:", [match_a, match_b], "#x")
+    assert "Alpha" in status
+    assert "Bravo" in status
+    assert match_a.url in status
+    assert match_b.url in status
+    assert status.count("Alpha") == 1
+    assert status.count("Bravo") == 1
+    assert status.count(match_a.url) == 1
+    assert status.count(match_b.url) == 1
+
+
+def test_build_status_text_empty_posts_raises() -> None:
+    with pytest.raises(PublishError):
+        build_status_text("P:", [], "#x")
+
+
+def test_build_status_text_preserves_deterministic_order() -> None:
+    match_a = _make_match("2016/2016-08-05-a.md", "Alpha", day=5)
+    match_b = _make_match("2016/2016-08-04-b.md", "Bravo", day=4)
+    forward = build_status_text("P:", [match_a, match_b], "#x")
+    reverse = build_status_text("P:", [match_b, match_a], "#x")
+    assert forward == reverse
+    assert forward.index("Bravo") < forward.index("Alpha")
+
+
+def test_validate_status_within_limit() -> None:
+    validate_status("a" * 480)
+
+
+def test_validate_status_over_limit_raises_and_does_not_truncate() -> None:
+    long = "a" * (MASTODON_STATUS_LIMIT + 1)
+    with pytest.raises(PublishError):
+        validate_status(long)
+    assert len(long) == MASTODON_STATUS_LIMIT + 1
+
+
+def test_publish_mastodon_success_invokes_client_with_composed_status(
+    full_config,
+) -> None:
+    match = _make_match("2016/2016-08-04-foo.md", "Foo")
+    fake = _FakeMastodon()
+
+    result = publish_mastodon(full_config, [match], client_factory=fake)
+
+    assert result.endswith("\n")
+    assert fake.calls, "status_post must be invoked"
+    posted_status, posted_kwargs = fake.calls[0]
+    assert posted_status == result
+    assert posted_kwargs == {"visibility": "public"}
+    assert fake.api_base_url == "https://mastodon.example"
+    assert fake.access_token == "test-token"
+
+
+def test_publish_mastodon_api_failure_raises_and_does_not_persist(
+    full_config, tmp_path: Path
+) -> None:
+    match = _make_match("2016/2016-08-04-foo.md", "Foo")
+    fake = _FakeMastodon(raise_on_post=RuntimeError("boom"))
+
+    with pytest.raises(PublishError) as exc_info:
+        publish_mastodon(full_config, [match], client_factory=fake)
+
+    assert "publish_failed" in str(exc_info.value)
+    assert isinstance(exc_info.value.__cause__, RuntimeError)
+
+    store = PostedStore(tmp_path)
+    assert not store.is_posted(match.path)
+
+
+def test_publish_mastodon_over_limit_raises_before_api_call(
+    full_config,
+) -> None:
+    long_title = "T" * (MASTODON_STATUS_LIMIT + 1)
+    match = MatchedPost(
+        path="2016/2016-08-04-foo.md",
+        title=long_title,
+        date=date(2016, 8, 4),
+        url="https://blog.example.com/2016/08/04/foo/",
+    )
+    fake = _FakeMastodon()
+
+    with pytest.raises(PublishError):
+        publish_mastodon(full_config, [match], client_factory=fake)
+
+    assert fake.calls == []
+
+
+def test_publish_mastodon_combined_status_for_multiple_matches(full_config) -> None:
+    match_a = _make_match("2016/2016-08-04-a.md", "Alpha")
+    match_b = _make_match("2016/2016-08-04-b.md", "Bravo")
+    fake = _FakeMastodon()
+
+    publish_mastodon(full_config, [match_a, match_b], client_factory=fake)
+
+    assert len(fake.calls) == 1
+    status, _ = fake.calls[0]
+    assert "Alpha" in status
+    assert "Bravo" in status
+    assert match_a.url in status
+    assert match_b.url in status
+
+
+def test_publish_mastodon_uses_config_visibility(env_setup, tmp_path: Path) -> None:
+    os.environ["VISIBILITY"] = "unlisted"
+    os.environ["DATA_DIR"] = str(tmp_path)
+    config = load_config()
+    match = _make_match("2016/2016-08-04-foo.md", "Foo")
+    fake = _FakeMastodon()
+
+    publish_mastodon(config, [match], client_factory=fake)
+
+    assert fake.calls[0][1] == {"visibility": "unlisted"}

tests/test_run_logging.py

@@ -8,9 +8,22 @@ from pathlib import Path
 
 import pytest
 
+from datetime import date
+
 from tenbackward import main as main_module
 from tenbackward.logging_setup import JsonFormatter
 from tenbackward.main import main
+from tenbackward.matching import MatchedPost
+from tenbackward.publishing import PublishError
+
+
+def _match(path: str) -> MatchedPost:
+    return MatchedPost(
+        path=path,
+        title=path,
+        date=date(2016, 8, 4),
+        url=f"https://blog.example.com/2016/08/04/{path.split('-', 3)[-1].removesuffix('.md')}/",
+    )
 
 
 @pytest.fixture()
@@ -38,7 +51,11 @@ def _seed_state(data_dir: Path, ids: list[str]) -> None:
 def test_run_emits_one_info_summary_on_success(env_setup, data_dir, capture_logger, monkeypatch) -> None:
     monkeypatch.setenv("DATA_DIR", str(data_dir))
 
-    monkeypatch.setattr(main_module, "_iter_candidates", lambda config: ["new-1", "already-1"])
+    def _stub_publish(config, posts, **_kwargs):
+        return "stubbed"
+
+    monkeypatch.setattr(main_module, "_iter_candidates", lambda config: [_match("new-1"), _match("already-1")])
+    monkeypatch.setattr(main_module, "publish_mastodon", _stub_publish)
 
     _seed_state(data_dir, ["already-1"])
 
@@ -100,7 +117,12 @@ def test_run_distinguishes_posted_from_skipped_via_ids(env_setup, data_dir, capt
     monkeypatch.setattr(
         main_module,
         "_iter_candidates",
-        lambda config: ["alpha", "beta", "gamma"],
+        lambda config: [_match("alpha"), _match("beta"), _match("gamma")],
+    )
+    monkeypatch.setattr(
+        main_module,
+        "publish_mastodon",
+        lambda config, posts, **_kwargs: "stubbed",
     )
     _seed_state(data_dir, ["beta"])
 
@@ -114,3 +136,28 @@ def test_run_distinguishes_posted_from_skipped_via_ids(env_setup, data_dir, capt
     assert "beta" not in payload["posted_ids"]
     assert payload["skipped"] == 1
     assert payload["posted"] == 2
+
+
+def test_run_publish_failure_leaves_state_untouched(
+    env_setup, data_dir, capture_logger, monkeypatch
+) -> None:
+    monkeypatch.setenv("DATA_DIR", str(data_dir))
+
+    def _boom(config, posts, **_kwargs):
+        raise PublishError("publish_failed: stub")
+
+    monkeypatch.setattr(main_module, "_iter_candidates", lambda config: [_match("alpha")])
+    monkeypatch.setattr(main_module, "publish_mastodon", _boom)
+
+    rc = main()
+    assert rc != 0
+
+    from tenbackward.state import load_posted
+
+    assert load_posted(data_dir) == []
+    error_lines = [
+        line
+        for line in _run_lines(capture_logger)
+        if line.get("level") == "ERROR"
+    ]
+    assert any(line.get("event") == "pipeline_error" for line in error_lines)